Advances in spatiotemporal graph neural network prediction research
Being a kind of non-Euclidean data, spatiotemporal graph data exists everywhere from traffic flow, air quality index to crime case, etc. Unlike the raster data, the irregular and disordered characteristics of spatiotemporal graph data have attracted the research interest of scholars, with the predic...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2023.2220610 |
| _version_ | 1797678517205336064 |
|---|---|
| author | Yi Wang |
| author_facet | Yi Wang |
| author_sort | Yi Wang |
| collection | DOAJ |
| description | Being a kind of non-Euclidean data, spatiotemporal graph data exists everywhere from traffic flow, air quality index to crime case, etc. Unlike the raster data, the irregular and disordered characteristics of spatiotemporal graph data have attracted the research interest of scholars, with the prediction of spatiotemporal graph data being one of the research hot spots. The emergence of spatiotemporal graph neural networks (ST-GNNs) provides a new insight for solving the problem of obtaining spatial correlation for spatiotemporal graph data prediction while achieving state-of-the-art performance. In this paper, a comprehensive survey of research on ST-GNNs prediction domain is presented, where the background of ST-GNNs is introduced before the computational paradigm of ST-GNN is thoroughly reviewed. From the perspective of model construction, 59 well-known models in recent years are classified and discussed. Some of these models are further analyzed in terms of performance and efficiency. Subsequently, the categories and application fields of spatiotemporal graph data are summarized, providing a clear idea of technology selection for different applications. Finally, the evolution history and future direction of ST-GNNs are also summarized, to facilitate future researchers to timely understand the current state of prediction research by ST-GNNs. |
| first_indexed | 2024-03-11T23:00:00Z |
| format | Article |
| id | doaj.art-d867a92da9c841ffb8bfd90207d071b3 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T23:00:00Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-d867a92da9c841ffb8bfd90207d071b32023-09-21T14:57:13ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552023-12-011612034206610.1080/17538947.2023.22206102220610Advances in spatiotemporal graph neural network prediction researchYi Wang0Peking UniversityBeing a kind of non-Euclidean data, spatiotemporal graph data exists everywhere from traffic flow, air quality index to crime case, etc. Unlike the raster data, the irregular and disordered characteristics of spatiotemporal graph data have attracted the research interest of scholars, with the prediction of spatiotemporal graph data being one of the research hot spots. The emergence of spatiotemporal graph neural networks (ST-GNNs) provides a new insight for solving the problem of obtaining spatial correlation for spatiotemporal graph data prediction while achieving state-of-the-art performance. In this paper, a comprehensive survey of research on ST-GNNs prediction domain is presented, where the background of ST-GNNs is introduced before the computational paradigm of ST-GNN is thoroughly reviewed. From the perspective of model construction, 59 well-known models in recent years are classified and discussed. Some of these models are further analyzed in terms of performance and efficiency. Subsequently, the categories and application fields of spatiotemporal graph data are summarized, providing a clear idea of technology selection for different applications. Finally, the evolution history and future direction of ST-GNNs are also summarized, to facilitate future researchers to timely understand the current state of prediction research by ST-GNNs.http://dx.doi.org/10.1080/17538947.2023.2220610spatiotemporal graph neural network; prediction models; spatiotemporal graph data |
| spellingShingle | Yi Wang Advances in spatiotemporal graph neural network prediction research International Journal of Digital Earth spatiotemporal graph neural network; prediction models; spatiotemporal graph data |
| title | Advances in spatiotemporal graph neural network prediction research |
| title_full | Advances in spatiotemporal graph neural network prediction research |
| title_fullStr | Advances in spatiotemporal graph neural network prediction research |
| title_full_unstemmed | Advances in spatiotemporal graph neural network prediction research |
| title_short | Advances in spatiotemporal graph neural network prediction research |
| title_sort | advances in spatiotemporal graph neural network prediction research |
| topic | spatiotemporal graph neural network; prediction models; spatiotemporal graph data |
| url | http://dx.doi.org/10.1080/17538947.2023.2220610 |
| work_keys_str_mv | AT yiwang advancesinspatiotemporalgraphneuralnetworkpredictionresearch |